Blog

Insights on AI security, agentic systems, cloud defense, and modern red teaming — curated by the Cracken team.

Agentic AI

10 articles
Detect and stop AI-driven attacks before they reach real assets, with 97.8% reliability. Introducing Project BlackSea.
Agentic AI

Detect and stop AI-driven attacks before they reach real assets, with 97.8% reliability. Introducing Project BlackSea.

The autonomous tools built to attack can be turned on the operators running them. We turned the same weakness back on the attackers and built Project BlackSea, a honeypot for autonomous AI agents.

Agentic AIAI LabCISOs MUST-READRed Team Operations
Dario Pasquini
Dario Pasquini07/28/2026
Red-Teaming the Agentic Red-Teamer Part.2
Agentic AI

Red-Teaming the Agentic Red-Teamer Part.2

Sandboxing your agentic pentester feels safe — until it isn’t. We put Claude Code under the microscope, sandboxed and not, and show how manipulating the agent’s reasoning runs an untrusted binary past Seatbelt and bwrap — no sandbox escape required.

Agentic AIAI LabRed Team OperationsPen Testing
michal bazyli
michal bazyli06/24/2026
Red-Teaming the Agentic Red-Teamer Part.1
Agentic AI

Red-Teaming the Agentic Red-Teamer Part.1

Every cybersecurity firm now ships an autonomous pentest agent — but can you trust one to run loose on your machine? We built a honeypot and turned four leading agentic red-teamers against themselves: indirect prompt injection, reverse shells, and full host compromise.

Agentic AIAI LabRed Team OperationsPen Testing
michal bazyli
michal bazyli06/22/2026
Mythos Brought It to the Boardroom. Now Weaponize Defense.
Agentic AI

Mythos Brought It to the Boardroom. Now Weaponize Defense.

AI crossed a threshold with Mythos. Cracken CEO Artem Sorokin breaks down what actually changed, why reactive security is no longer viable, and how CISOs should operationalize adversarial exposure validation across the full kill chain.

Agentic AILLM AbliterationAEV
Artem Sorokin
Artem Sorokin05/15/2026
Cyber Capacity as a Systemic Model: Agent-Augmented Defense and Offense in DDIL Environments
Agentic AI

Cyber Capacity as a Systemic Model: Agent-Augmented Defense and Offense in DDIL Environments

AI “digital staff officers” transform cyber capacity in DDIL. This new framework aligns human intent, agent orchestration, Moving Target Defense, and PETIO for resilient, continuously validated cyber operations.

Agentic AIRed Team Operations
Jesse Nuese
Jesse Nuese02/23/2026
AI-Addicted Forensics: Back to Foundations
Agentic AI

AI-Addicted Forensics: Back to Foundations

The OpenClaw hype is real. We unleashed an AI agent on top of forensic foundations (Volatility, TSK, VirusTotal) and watched it uncover real breakthroughs — even a reverse shell — without being told where to look.

Agentic AIOpenClawAI LabAI Forensics
Oleksii Baranovskyi
Oleksii Baranovskyi02/12/2026
Weaponize Defense. Release The Cracken
Agentic AI

Weaponize Defense. Release The Cracken

Attackers don’t guess. They test. Cracken weaponizes defense with adversarial AI that proves what’s exploitable—right now. Less noise. More truth. Release the Cracken.

Agentic AIRed Team OperationsExposure ManagementAI Lab
GA
Guilherme Alvarenga12/17/2025
Ghost in the Neural Shell
AI Lab

Ghost in the Neural Shell

Anthropic showed tiny poisoned samples can implant backdoors in LLMs. I replicated this with GPT-2 using 50 poisoned examples, proving how easily training data tampering can compromise a model.

AI LabRed Team OperationsMechanistic InterpretabilityAgentic AI
michal bazyli
michal bazyli12/02/2025
The Domain-Specific Abliteration Paradox
Agentic AI

The Domain-Specific Abliteration Paradox

How abliterating cybersecurity refusal collapsed nearly every safety domain — despite near-zero vector similarity except for the one that shared the most overlap

Agentic AIMechanistic InterpretabilityAI Lab
Vadym Hadetskyi
Vadym Hadetskyi11/07/2025
Why CNAPP Fluff Won’t Save You: The Case for Red AI
Pen Testing

Why CNAPP Fluff Won’t Save You: The Case for Red AI

Agentic AI doesn’t hack, it learns. It studies your CNAPP reports, predicts your playbook, and rewrites your defense before you wake up. Posture won’t save you.

Pen TestingCloud SecurityAEVRed Team OperationsExposure ManagementAgentic AIAgentic LabCISOs MUST-READ
GA
Guilherme Alvarenga10/21/2025
Agentic AI – Blog | Cracken